Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3759 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8375. Min Range: -1.8375
Max Act: 1.8375. Min Act: -0.1700
Data Index: 1346931 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8375. Min Range: -1.8375
Max Act: 1.8290. Min Act: -0.1700
Data Index: 8409103 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8375. Min Range: -1.8375
Max Act: 1.8032. Min Act: -0.1700
Data Index: 2797577 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8375. Min Range: -1.8375
Max Act: 1.7946. Min Act: -0.1700
Data Index: 7636417 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8375. Min Range: -1.8375
Max Act: 1.7774. Min Act: -0.1700
Data Index: 7223349 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8375. Min Range: -1.8375
Max Act: 1.7687. Min Act: -0.1700
Data Index: 3231711 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8375. Min Range: -1.8375
Max Act: 1.7687. Min Act: -0.1700
Data Index: 8422069 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8375. Min Range: -1.8375
Max Act: 1.7774. Min Act: -0.1700
Data Index: 2882690 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8375. Min Range: -1.8375
Max Act: 1.7687. Min Act: -0.1700
Data Index: 4456399 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8375. Min Range: -1.8375
Max Act: 1.7687. Min Act: -0.1700
Data Index: 1915706 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8375. Min Range: -1.8375
Max Act: 1.7601. Min Act: -0.1700
Data Index: 6153232 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8375. Min Range: -1.8375
Max Act: 1.7601. Min Act: -0.1700
Data Index: 4880000 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8375. Min Range: -1.8375
Max Act: 1.7428. Min Act: -0.1700
Data Index: 280574 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8375. Min Range: -1.8375
Max Act: 1.7515. Min Act: -0.1700
Data Index: 1561882 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8375. Min Range: -1.8375
Max Act: 1.7255. Min Act: -0.1700
Data Index: 18341 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8375. Min Range: -1.8375
Max Act: 1.7515. Min Act: -0.1700
Data Index: 18339 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8375. Min Range: -1.8375
Max Act: 1.7428. Min Act: -0.1700
Data Index: 6013218 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8375. Min Range: -1.8375
Max Act: 1.7515. Min Act: -0.1700
Data Index: 3906815 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8375. Min Range: -1.8375
Max Act: 1.7342. Min Act: -0.1697
Data Index: 6219440 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8375. Min Range: -1.8375
Max Act: 1.7255. Min Act: -0.1700
Data Index: 218729 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19